Linux-3.14.12内存管理笔记【伙伴管理算法（1）】

前面分析了memblock算法、内核页表的建立、内存管理框架的构建，这些都是x86处理的setup_arch()函数里面初始化的，因地制宜，具有明显处理器的特征。而start_kernel()接下来的初始化则是linux通用的内存管理算法框架了。

build_all_zonelists()用来初始化内存分配器使用的存储节点中的管理区链表，是为内存管理算法（伙伴管理算法）做准备工作的。具体实现：

【file：/mm/page_alloc.c】
/*
 * Called with zonelists_mutex held always
 * unless system_state == SYSTEM_BOOTING.
 */
void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
{
    set_zonelist_order();

    if (system_state == SYSTEM_BOOTING) {
        __build_all_zonelists(NULL);
        mminit_verify_zonelist();
        cpuset_init_current_mems_allowed();
    } else {
#ifdef CONFIG_MEMORY_HOTPLUG
        if (zone)
            setup_zone_pageset(zone);
#endif
        /* we have to stop all cpus to guarantee there is no user
           of zonelist */
        stop_machine(__build_all_zonelists, pgdat, NULL);
        /* cpuset refresh routine should be here */
    }
    vm_total_pages = nr_free_pagecache_pages();
    /*
     * Disable grouping by mobility if the number of pages in the
     * system is too low to allow the mechanism to work. It would be
     * more accurate, but expensive to check per-zone. This check is
     * made on memory-hotadd so a system can start with mobility
     * disabled and enable it later
     */
    if (vm_total_pages < (pageblock_nr_pages * MIGRATE_TYPES))
        page_group_by_mobility_disabled = 1;
    else
        page_group_by_mobility_disabled = 0;

    printk("Built %i zonelists in %s order, mobility grouping %s.  "
        "Total pages: %ld\n",
            nr_online_nodes,
            zonelist_order_name[current_zonelist_order],
            page_group_by_mobility_disabled ? "off" : "on",
            vm_total_pages);
#ifdef CONFIG_NUMA
    printk("Policy zone: %s\n", zone_names[policy_zone]);
#endif
}

    首先看到set_zonelist_order()：

【file：/mm/page_alloc.c】
static void set_zonelist_order(void)
{
    current_zonelist_order = ZONELIST_ORDER_ZONE;
}

此处用于设置zonelist的顺序，ZONELIST_ORDER_ZONE用于表示顺序(-zonetype, [node] distance)，另外还有ZONELIST_ORDER_NODE表示顺序([node] distance, -zonetype)。但其仅限于对NUMA环境存在区别，非NUMA环境则毫无差异。

如果系统状态system_state为SYSTEM_BOOTING，系统状态只有在start_kernel执行到最后一个函数rest_init后，才会进入SYSTEM_RUNNING，于是初始化时将会接着是__build_all_zonelists()函数:

【file：/mm/page_alloc.c】
/* return values int ....just for stop_machine() */
static int __build_all_zonelists(void *data)
{
    int nid;
    int cpu;
    pg_data_t *self = data;

#ifdef CONFIG_NUMA
    memset(node_load, 0, sizeof(node_load));
#endif

    if (self && !node_online(self->node_id)) {
        build_zonelists(self);
        build_zonelist_cache(self);
    }

    for_each_online_node(nid) {
        pg_data_t *pgdat = NODE_DATA(nid);

        build_zonelists(pgdat);
        build_zonelist_cache(pgdat);
    }

    /*
     * Initialize the boot_pagesets that are going to be used
     * for bootstrapping processors. The real pagesets for
     * each zone will be allocated later when the per cpu
     * allocator is available.
     *
     * boot_pagesets are used also for bootstrapping offline
     * cpus if the system is already booted because the pagesets
     * are needed to initialize allocators on a specific cpu too.
     * F.e. the percpu allocator needs the page allocator which
     * needs the percpu allocator in order to allocate its pagesets
     * (a chicken-egg dilemma).
     */
    for_each_possible_cpu(cpu) {
        setup_pageset(&per_cpu(boot_pageset, cpu), 0);

#ifdef CONFIG_HAVE_MEMORYLESS_NODES
        /*
         * We now know the "local memory node" for each node--
         * i.e., the node of the first zone in the generic zonelist.
         * Set up numa_mem percpu variable for on-line cpus. During
         * boot, only the boot cpu should be on-line; we'll init the
         * secondary cpus' numa_mem as they come on-line. During
         * node/memory hotplug, we'll fixup all on-line cpus.
         */
        if (cpu_online(cpu))
            set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu)));
#endif
    }

    return 0;
}

    首先分析该函数里面调用的build_zonelists()和build_zonelist_cache()函数，其中build_zonelists()：

【file：/mm/page_alloc.c】
static void build_zonelists(pg_data_t *pgdat)
{
    int node, local_node;
    enum zone_type j;
    struct zonelist *zonelist;

    local_node = pgdat->node_id;

    zonelist = &pgdat->node_zonelists[0];
    j = build_zonelists_node(pgdat, zonelist, 0);

    /*
     * Now we build the zonelist so that it contains the zones
     * of all the other nodes.
     * We don't want to pressure a particular node, so when
     * building the zones for node N, we make sure that the
     * zones coming right after the local ones are those from
     * node N+1 (modulo N)
     */
    for (node = local_node + 1; node < MAX_NUMNODES; node++) {
        if (!node_online(node))
            continue;
        j = build_zonelists_node(NODE_DATA(node), zonelist, j);
    }
    for (node = 0; node < local_node; node++) {
        if (!node_online(node))
            continue;
        j = build_zonelists_node(NODE_DATA(node), zonelist, j);
    }

    zonelist->_zonerefs[j].zone = NULL;
    zonelist->_zonerefs[j].zone_idx = 0;
}

    其中build_zonelists_node()函数实现：

【file：/mm/page_alloc.c】
/*
 * Builds allocation fallback zone lists.
 *
 * Add all populated zones of a node to the zonelist.
 */
static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
                int nr_zones)
{
    struct zone *zone;
    enum zone_type zone_type = MAX_NR_ZONES;

    do {
        zone_type--;
        zone = pgdat->node_zones + zone_type;
        if (populated_zone(zone)) {
            zoneref_set_zone(zone,
                &zonelist->_zonerefs[nr_zones++]);
            check_highest_zone(zone_type);
        }
    } while (zone_type);

    return nr_zones;
}

populated_zone()用于判断管理区zone的present_pages成员是否为0，如果不为0的话，表示该管理区存在页面，那么则通过zoneref_set_zone()将其设置到zonelist的_zonerefs里面，而check_highest_zone()在没有开启NUMA的情况下是个空函数。由此可以看出build_zonelists_node()实则上是按照ZONE_HIGHMEM—>ZONE_NORMAL—>ZONE_DMA的顺序去迭代排布到_zonerefs里面的，表示一个申请内存的代价由低廉到昂贵的顺序，这是一个分配内存时的备用次序。

回到build_zonelists()函数中，而它代码显示将本地的内存管理区进行分配备用次序排序，接着再是分配内存代价低于本地的，最后才是分配内存代价高于本地的。

分析完build_zonelists()，再回到__build_all_zonelists()看一下build_zonelist_cache()：

【file：/mm/page_alloc.c】
/* non-NUMA variant of zonelist performance cache - just NULL zlcache_ptr */
static void build_zonelist_cache(pg_data_t *pgdat)
{
    pgdat->node_zonelists[0].zlcache_ptr = NULL;
}

该函数与CONFIG_NUMA相关，用来设置zlcache相关的成员。由于没有开启该配置，故直接设置为NULL。

基于build_all_zonelists()调用__build_all_zonelists()入参为NULL，由此可知__build_all_zonelists()运行的代码是：

    for_each_online_node(nid) {

        pg_data_t *pgdat = NODE_DATA(nid);

        build_zonelists(pgdat);

        build_zonelist_cache(pgdat);

    }

主要是设置各个内存管理节点node里面各自的内存管理分区zone的内存分配次序。

__build_all_zonelists()接着的是：

    for_each_possible_cpu(cpu) {

        setup_pageset(&per_cpu(boot_pageset, cpu), 0);

#ifdef CONFIG_HAVE_MEMORYLESS_NODES

        if (cpu_online(cpu))

            set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu)));

#endif

    }

其中CONFIG_HAVE_MEMORYLESS_NODES未配置，主要分析一下setup_pageset()：

【file：/mm/page_alloc.c】
static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
{
    pageset_init(p);
    pageset_set_batch(p, batch);
}

setup_pageset()里面调用的两个函数较为简单，就直接过一下。先是：

【file：/mm/page_alloc.c】
static void pageset_init(struct per_cpu_pageset *p)
{
    struct per_cpu_pages *pcp;
    int migratetype;

    memset(p, 0, sizeof(*p));

    pcp = &p->pcp;
    pcp->count = 0;
    for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++)
        INIT_LIST_HEAD(&pcp->lists[migratetype]);
}

    pageset_init()主要是将struct per_cpu_pages结构体进行初始化，而pageset_set_batch()则是对其进行设置。pageset_set_batch()实现：

【file：/mm/page_alloc.c】
/*
 * pcp->high and pcp->batch values are related and dependent on one another:
 * ->batch must never be higher then ->high.
 * The following function updates them in a safe manner without read side
 * locking.
 *
 * Any new users of pcp->batch and pcp->high should ensure they can cope with
 * those fields changing asynchronously (acording the the above rule).
 *
 * mutex_is_locked(&pcp_batch_high_lock) required when calling this function
 * outside of boot time (or some other assurance that no concurrent updaters
 * exist).
 */
static void pageset_update(struct per_cpu_pages *pcp, unsigned long high,
        unsigned long batch)
{
       /* start with a fail safe value for batch */
    pcp->batch = 1;
    smp_wmb();

       /* Update high, then batch, in order */
    pcp->high = high;
    smp_wmb();

    pcp->batch = batch;
}

/* a companion to pageset_set_high() */
static void pageset_set_batch(struct per_cpu_pageset *p, unsigned long batch)
{
    pageset_update(&p->pcp, 6 * batch, max(1UL, 1 * batch));
}

setup_pageset()函数入参p是一个struct per_cpu_pageset结构体的指针，per_cpu_pageset结构是内核的各个zone用于每CPU的页面高速缓存管理结构。该高速缓存包含一些预先分配的页面，以用于满足本地CPU发出的单一内存请求。而struct per_cpu_pages定义的pcp是该管理结构的成员，用于具体页面管理。原本是每个管理结构有两个pcp数组成员，里面的两条队列分别用于冷页面和热页面管理，而当前分析的3.14.12版本已经将两者合并起来，统一管理冷热页，热页面在队列前面，而冷页面则在队列后面。暂且先记着这么多，后续在Buddy算法的时候再详细分析了。

至此，可以知道__build_all_zonelists()是内存管理框架向后续的内存页面管理算法做准备，排布了内存管理区zone的分配次序，同时初始化了冷热页管理。

     最后回到build_all_zonelists()函数。由于没有开启内存初始化调试功能CONFIG_DEBUG_MEMORY_INIT，mminit_verify_zonelist()是一个空函数。

基于CONFIG_CPUSETS配置项开启的情况下，而cpuset_init_current_mems_allowed()实现如下：

【file：/kernel/cpuset.c】
void cpuset_init_current_mems_allowed(void)
{
    nodes_setall(current->mems_allowed);
}

这里面的current 是一个cpuset的数据结构，用来管理cgroup中的任务能够使用的cpu和内存节点。而成员mems_allowed，该成员是nodemask_t类型的结构体：

【file：/include/linux/nodemask.h】
typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;

该结构其实就是定义了一个位域，每个位对应一个内存结点，如果置1表示该节点内存可用。而nodes_setall则是将这个位域中每个位都置1。

末了看一下build_all_zonelists()里面nr_free_pagecache_pages()的实现：

【file：/mm/page_alloc.c】
/**
 * nr_free_pagecache_pages - count number of pages beyond high watermark
 *
 * nr_free_pagecache_pages() counts the number of pages which are beyond the
 * high watermark within all zones.
 */
unsigned long nr_free_pagecache_pages(void)
{
    return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE));
}

而里面调用的nr_free_zone_pages()实现为：

【file：/mm/page_alloc.c】
/**
 * nr_free_zone_pages - count number of pages beyond high watermark
 * @offset: The zone index of the highest zone
 *
 * nr_free_zone_pages() counts the number of counts pages which are beyond the
 * high watermark within all zones at or below a given zone index. For each
 * zone, the number of pages is calculated as:
 * managed_pages - high_pages
 */
static unsigned long nr_free_zone_pages(int offset)
{
    struct zoneref *z;
    struct zone *zone;

    /* Just pick one node, since fallback list is circular */
    unsigned long sum = 0;

    struct zonelist *zonelist = node_zonelist(numa_node_id(), GFP_KERNEL);

    for_each_zone_zonelist(zone, z, zonelist, offset) {
        unsigned long size = zone->managed_pages;
        unsigned long high = high_wmark_pages(zone);
        if (size > high)
            sum += size - high;
    }

    return sum;
}

可以看到nr_free_zone_pages()遍历所有内存管理区并将各管理区的内存空间求和，其实质是用于统计所有的管理区可以用于分配的内存页面数。

接着在build_all_zonelists()后面则是判断当前系统中的内存页框数目，以决定是否启用流动分组机制(Mobility Grouping)，该机制可以在分配大内存块时减少内存碎片。通常只有内存足够大时才会启用该功能，否则将会提升消耗降低性能。其中pageblock_nr_pages表示伙伴系统中的最高阶页块所能包含的页面数。

至此，内存管理框架算法基本准备完毕。